A Case Study on Coupling OpenFOAM with Different Machine Learning Frameworks
- 1 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7-12
Abstract
In High-Performance Computing, new use cases are currently emerging in which classical numerical simulations are coupled with machine learning as a surrogate for complex physical models that are expensive to compute. In the context of simulating reactive thermo-fluid systems, the idea to replace current state-of-the-art tabulated chemistry with machine learning inference is an active field of research. For this purpose, a simplified OpenFOAM application is coupled with an artificial neural network. In this work, we present a case study focusing solely on the performance of the coupled OpenFOAM-ML application. Our coupling approach features a heterogeneous cluster architecture combining pure CPU nodes and nodes equipped with two Nvidia V100 GPUs. We evaluate our approach by comparing the inference performance and the communication our approach induces with various machine learning frameworks. Additionally, we also compare the GPUs with NEC Vector Engine Type 10B regarding inference performance.Keywords
Funding Information
- German Federal Ministry of Education and Research
- state governments of North Rhine-Westphalia (951733)
This publication has 12 references indexed in Scilit:
- Speed-Up of Machine Learning for Sound Localization via High-Performance Computing2022
- A High-Performance Multispectral Adaptation GAN for Harmonizing Dense Time Series of Landsat-8 and Sentinel-2 ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
- GPU-Accelerated Machine Learning Inference as a Service for Computing in Neutrino ExperimentsFrontiers in Big Data, 2021
- Tabulation of combustion chemistry via Artificial Neural Networks (ANNs): Methodology and application to LES-PDF simulation of Sydney flame LCombustion and Flame, 2017
- In-Datacenter Performance Analysis of a Tensor Processing UnitACM SIGARCH Computer Architecture News, 2017
- State-of-the-art in premixed combustion modeling using flamelet generated manifoldsProgress in Energy and Combustion Science, 2016
- Reducing the memory footprint in Large Eddy Simulations of reactive flowsParallel Computing, 2015
- Accelerating multi-dimensional combustion simulations using GPU and hybrid explicit/implicit ODE integrationCombustion and Flame, 2012
- RooflineCommunications of the ACM, 2009
- Steady and Unsteady Flow Simulations Using the Hybrid Flow Solver AVBPAIAA Journal, 1999